
# importing python libraries to use for analysis

import pandas as pd # panel data
import numpy as np # numerical python, for transformations
import matplotlib.pyplot as plt # matplotlib for plotting
import seaborn as sns # seaborn for plotting
import re # regex match patterns
from better_profanity import profanity
from textblob import TextBlob 
from wordcloud import WordCloud # wordcloud for visualizing significant terms each review
from collections import Counter # counter for words count
import string
import plotly.express as px # interactive plots
from plotly.subplots import make_subplots
import plotly.graph_objects as go


# load in the df prepared in "data_prep" notebook - AIB branches in Dublin and summary of google reviews

df = pd.read_csv("../data/aib_banks_dublin_cleaned_reviews.csv")
df.head()


# remove rows with missing values, labelled as '-'
df = df[df['google_rating'] != '-']

# in this case will take reviews from the top ranked and lowest ranked branches without taking 
# number of reviews in to account, if taking that in to account could use Bayesian average

df.sort_values('google_rating', inplace=True)
df.head()


# first define a function that will prepare the reviews for analysis. Each review is a single line in the txt file

def clean_review(review):
    # Check for missing values
    if review is np.nan:
        return ""
    
    # Convert to lowercase
    cleaned_review = review.lower()
    
    # remove profanity
    cleaned_review = profanity.censor(cleaned_review)
    
    # Remove URLs
    cleaned_review = re.sub(r'http\S+', '', cleaned_review)
    
    # Remove special characters, punctuation, and non-alphanumeric characters
    cleaned_review = re.sub(r'[^a-z0-9 ]', ' ', cleaned_review)
    
    # Split the review into words
    words = cleaned_review.split()
    
    # Define a list of stopwords to remove
    stopwords = ["for", "on", "an", "a", "of", "and", "in", "the", "to", "from"]
    
    # Remove stopwords
    words = [word for word in words if word not in stopwords]
    
    # Join the cleaned words back into a string
    cleaned_review = " ".join(words)
    
    return cleaned_review


# Read reviews from the text files into a list
def read_reviews_from_file(file_path):
    with open(file_path, 'r', encoding='utf-8') as file:
        reviews = [line.strip() for line in file]
    return reviews

# Clean the reviews and store them in a new list
def clean_reviews(reviews):
    cleaned_reviews = [clean_review(review) for review in reviews]
    return cleaned_reviews


# load in our higher and lower ranked reviews

file_path_higher = '../data/higher_scores/merged_higher.txt'
file_path_lower = "../data/lower_scores/merged_lower.txt"
reviews_higher = read_reviews_from_file(file_path_higher)
reviews_lower = read_reviews_from_file(file_path_lower)

cleaned_reviews_higher = clean_reviews(reviews_higher)
cleaned_reviews_lower = clean_reviews(reviews_lower)


# have a look at some sample lines from the cleaned reviews

print(cleaned_reviews_higher[0:2], cleaned_reviews_lower[0:2])

['all good', 'we ve been served by morgan she was so helpful friendly it literally took 5 mins complete everything best aib experience'] ['most pointless bank around go make lodgement you re told go across post office they can t help you with any day day banking needs avoid', 'very good bank they do help you out']


# Define the sentiment objects using TextBlob

sentiment_objects_higher = [TextBlob(review) for review in cleaned_reviews_higher]
sentiment_objects_lower = [TextBlob(review) for review in cleaned_reviews_lower]

# Create a list of polarity values and review text

sentiment_values_higher = [[review.sentiment.polarity, str(review)] for review in sentiment_objects_higher]
sentiment_values_lower = [[review.sentiment.polarity, str(review)] for review in sentiment_objects_lower]


# Create a dataframe of each review against its polarity

sentiment_df_higher = pd.DataFrame(sentiment_values_higher, columns=["polarity", "review"])
sentiment_df_lower = pd.DataFrame(sentiment_values_lower, columns=["polarity", "review"])


sentiment_df_higher.head() # look of the sentiment dataframe


# Save the polarity column as 'n'.

n_high = sentiment_df_higher["polarity"]
n_low = sentiment_df_lower["polarity"]

# Convert this column into a series, 'm'. 
m_high = pd.Series(n_high)
m_low = pd.Series(n_low)


# initialize three variables, ‘pos’, ‘neg’ and ‘neu’. Use these variables to create a loop to classify 
# the tweets as positive, negative, and neutral.

pos_h=0
neg_h=0
neu_h=0
pos_l=0
neg_l=0
neu_l=0

# Create a loop to classify the tweets as Positive, Negative, or Neutral.
# Count the number of each.

for items in m_high:
    if items>0:
        pos_h=pos_h+1
    elif items<0:
        neg_h=neg_h+1
    else:
        neu_h=neu_h+1

for items in m_low:
    if items>0:
        pos_l=pos_l+1
    elif items<0:
        neg_l=neg_l+1
    else:
        neu_l=neu_l+1


# Data for high ranking
labels_high = ["Positive", "Negative", "Neutral"]
sizes_high = [pos_h, neg_h, neu_h]

# Data for low ranking
labels_low = ["Positive", "Negative", "Neutral"]
sizes_low = [pos_l, neg_l, neu_l]

# Create subplot
fig = make_subplots(1, 2, specs=[[{'type':'pie'}, {'type':'pie'}]])

# Create chart for high ranking branches
fig.add_trace(go.Pie(labels=labels_high, values=sizes_high, title="High Ranking Branches"), row=1, col=1)

# Create chart for low ranking branches
fig.add_trace(go.Pie(labels=labels_low, values=sizes_low, title="Low Ranking Branches"), row=1, col=2)

# Update layout 
fig.update_layout(title_text="Sentiment Polarity for Reviews from High and Low Ranking Branches", 
title_x = 0.5, annotations=[dict(x=0.5, y=-0.1, text="Figure 1. Sentiment polarity for high ranking branches vs lower ranking branches.",
showarrow=False, xref="paper",yref="paper", font=dict(size=16),),])


# Display
fig.show()


# Create a Wordcloud from the reviews

#remove some common words including domain specific ones which will be there like 'bank' etc

common_stopwords = [
    "i", "me", "my", "myself", "we", "our", "ours", "ourselves",
    "you", "your", "yours", "yourself", "yourselves",
    "he", "him", "his", "himself", "she", "her", "hers", "herself",
    "it", "its", "itself", "they", "them", "their", "theirs", "themselves",
    "what", "which", "who", "whom", "this", "that", "these", "those",
    "am", "is", "are", "was", "were", "be", "been", "being", "have", "has", "had",
    "do", "does", "did", "doing", "a", "an", "the", "and", "but", "if", "or",
    "because", "as", "until", "while", "of", "at", "by", "for", "with", "about",
    "against", "between", "into", "through", "during", "before", "after", "above",
    "below", "to", "from", "up", "down", "in", "out", "on", "off", "over", "under",
    "again", "further", "then", "once", "here", "there", "when", "where", "why",
    "how", "all", "any", "both", "each", "few", "more", "most", "other", "some", "such",
    "no", "nor", "not", "only", "own", "same", "so", "than", "too", "very", "s", "t",
    "can", "will", "just", "don", "should", "now", "d", "ll", "m", "o", "re", "ve", "y",
    "ain", "aren", "couldn", "didn", "doesn", "hadn", "hasn", "haven", "isn", "ma", "mightn",
    "mustn", "needn", "shan", "shouldn", "wasn", "weren", "won", "wouldn", "bank","account",
    "branch","service",'go',"customer","get","banking","aib","use","time","went","need","needed","would",
    "told", "staff", "one"
]

# Create a Wordcloud from the high-ranking reviews
all_words_high = ' '.join([text for text in cleaned_reviews_higher])
wordcloud_high = WordCloud(width=480, height=500, random_state=21,max_font_size=110,colormap='viridis', background_color='white', stopwords=common_stopwords).generate(all_words_high)

# Create a Wordcloud from the low-ranking reviews
all_words_low = ' '.join([text for text in cleaned_reviews_lower])
wordcloud_low = WordCloud(width=480, height=500, random_state=21, max_font_size=110, colormap='viridis', background_color='white',stopwords=common_stopwords).generate(all_words_low)

# Create a subplot layout
fig, axes = plt.subplots(1, 2, figsize=(12, 6))

# Display the high-ranking word cloud in the first subplot 
axes[0].imshow(wordcloud_high, interpolation="bilinear")
axes[0].set_title("High Ranking Reviews")
axes[0].axis('off')

# Display low-ranking word cloud in the second subplot
axes[1].imshow(wordcloud_low, interpolation="bilinear")
axes[1].set_title("Low Ranking Reviews")
axes[1].axis('off')

# title and caption
plt.suptitle("Wordcloud for Reviews from High/Low Ranking Branches", fontsize=16, y = 1.02)
fig.text(0.5, -0.1, 'Figure 2. Wordcloud for high ranking branches vs lower ranking branches.', fontsize=15, ha='center')


# Show plot
plt.tight_layout()
plt.show()


# take all the words from the reviews and split them using spaces

high_words = all_words_high.split(' ')
low_words = all_words_low.split(' ')


# use the same stopword filter that was used for the wordcloud above
high_without_stopwords = [ word for word in high_words if word not in common_stopwords ]
low_without_stopwords = [ word for word in low_words if word not in common_stopwords ]


# Get the top 10 most common words in each set of reviews
top_words_high = Counter(high_without_stopwords).most_common(10)
top_words_low = Counter(low_without_stopwords).most_common(10)

# Unpack tuples to separate words and frequencies
words_high, frequencies_high = zip(*top_words_high)
words_low, frequencies_low = zip(*top_words_low)

# Create a subplot with two horizontal bar charts side by side
fig = fig = make_subplots(rows=1, cols=2, column_widths=[0.5, 0.5])

# Add bar chart for highest-ranked review words
fig.add_trace(go.Bar(y=words_high, x=frequencies_high, orientation='h', marker_color='limegreen', name="High Ranked"), row=1, col=1)

# Add bar chart for lowest-ranked review words
fig.add_trace(go.Bar(y=words_low, x=frequencies_low, orientation='h', marker_color='tomato', name="Low Ranked"), row=1, col=2)

# Update layout
fig.update_layout(
    title_text="Comparison of Top 10 Words in High and Low Ranked Reviews",
    title_x=0.5,
    annotations=[
        # Add a caption
        dict(
            x=0.5,  # adjust position
            y=-0.225,  
            text="Figure 3. Top 10 words in high and low ranked reviews.",
            showarrow=False,
            xref="paper",
            yref="paper",
            font=dict(size=16),
        ), 
    ], width = 900
)

# Update x-axis titles
fig.update_xaxes(title_text="Frequency (High Ranked)", row=1, col=1)
fig.update_xaxes(title_text="Frequency (Low Ranked)", row=1, col=2)

# Display 
fig.show()

	name	location	number	google_rating	num_reviews
0	AIB Bank	100 101 Grafton Street	(01) 671 3011	2.9	109
1	AIB Bank	7/12 Dame St	(01) 679 3211	2.9	45
2	AIB IFSC	Dublin 1	(01) 829 1880	4	1
3	AIB Bank	61 Richmond St S	(01) 478 4533	1.9	49
4	AIB Bank	126 128 Capel St	(01) 872 1022	3.3	127

	name	location	number	google_rating	num_reviews
3	AIB Bank	61 Richmond St S	(01) 478 4533	1.9	49
5	AIB Bank	Cabra County Dublin	(01) 868 0071	2.2	56
29	AIB Bank	County Dublin	(01) 490 4607	2.2	19
27	AIB Bank	Blackrock County Dublin	(01) 288 0705	2.3	37
17	AIB Bank	Dublin 11	(01) 842 0285	2.3	15

	polarity	review
0	0.700000	all good
1	0.491667	we ve been served by morgan she was so helpful...
2	0.386905	had pleasure dining buddha mama last saturday ...
3	-0.016667	tried lodge cheque machine froze 5 minutes eve...
4	0.200000	maria victor grateful staf thanks your help yo...

AIB Evaluation in Dublin:

A Comparative Analysis of Customer Reviews and Ratings

Aim of this Notebook¶

Methodology¶

Data Collection¶

Data Processing¶

Data Sources¶

Results¶

High-Ranked Branches¶

Low-Ranked Branches¶

Conclusions¶

Selecting branches for review collection¶

Cleaning and filtering reviews for sentiment analysis¶

Sentiment analysis of reviews¶

Figures displaying sentiment analysis and word counts for reviews¶

Creating a 'wordcloud' using the reviews for both rankings¶

Counting words associated with good and bad reviews¶

AIB Evaluation in Dublin: A Comparative Analysis of Customer Reviews and Ratings

Aim of this Notebook¶

Methodology¶

Data Collection¶

Data Processing¶

Data Sources¶

Results¶

High-Ranked Branches¶

Low-Ranked Branches¶

Conclusions¶

Selecting branches for review collection¶

Cleaning and filtering reviews for sentiment analysis¶

Sentiment analysis of reviews¶

Figures displaying sentiment analysis and word counts for reviews¶

Creating a 'wordcloud' using the reviews for both rankings¶

Counting words associated with good and bad reviews¶

AIB Evaluation in Dublin:

A Comparative Analysis of Customer Reviews and Ratings